Evolutionary Learning of Fuzzy Control in Robot-Soccer

Author(s):  
P. J. Thomas ◽  
R. J. Stonier

In this chapter an evolutionary algorithm is developed to learn a fuzzy knowledge base for the control of a soccer micro-robot from any configuration belonging to a grid of initial configurations, to hit the ball along the ball to goal line of sight. A relative coordinate system is used. Forward and reverse mode of the robot and its physical dimensions are incorporated, as well as special considerations to cases when in its initial configuration, the robot is touching the ball.

2013 ◽  
Vol 284-287 ◽  
pp. 2085-2091
Author(s):  
Chyi Yeu Lin ◽  
Jinn Feng Jiang ◽  
Yi Jie Chen ◽  
Hung Yuan Wei ◽  
Cheng Hsien Wang

The present study proposes a windshield warning system for vehicles that marks potential hazardous objects in front via marks on the windshield. The target is identified by the camera and the software system and then used to construct the line-of-sight equation based on the coordinate system of the moving vehicle. The explicit equation of the intersection point of the line of sight and the windshield surface is derived using an algebraic method. A warning mark is then projected at the intersection point on the windshield by a two-degree-of-freedom laser projector, allowing the driver to easily identify the obstacle. The feasibility of the proposed system was verified using an actual vehicle. Results show that the system can perform the required function in real time.


Author(s):  
Pieter Spronck ◽  
Ida Sprinkhuizen-Kuyper ◽  
Eric Postma ◽  
Rens Kortmann

In our research we use evolutionary algorithms to evolve robot controllers for executing elementary behaviours. This chapter focuses on the behaviour of pushing a box between two walls. The main research question addressed in this chapter is: how can a neural network learn to control the box-pushing task using evolutionary-computation techniques? In answering this question we study the following three characteristics by means of simulation experiments: (1) the fitness function, (2) the neural network topology and (3) the parameters of the evolutionary algorithm. We find that appropriate choices for these characteristics are: (1) a global external fitness function, (2) a recurrent neural network, and (3) a regular evolutionary algorithm augmented with the doping technique in which the initial population is supplied with a solution to a hard task instance. We conclude by stating that our findings on the relatively simple box-pushing behaviour form a good starting point for the evolutionary learning of more complex behaviours.


2013 ◽  
Vol 397-400 ◽  
pp. 530-535 ◽  
Author(s):  
Hui Liu ◽  
Ming Chao Zhu ◽  
Bo Liu ◽  
Hong Guang Jia

Roll-pitch seeker is currently applied in particular missiles, especially in air to air missiles. A representation of the seeker gimbal forward kinematics is analysed for the roll-pitch seeker based on the product-of-exponentials (POE) formula. And by transforming the inertial angular rate into the line-of-sight (LOS) coordinate system with the aid of recursive angular velocity equations, the LOS stabilization equation is obtained, then various schemes of gyroscope configuration and control are put forward based on the gyro direct stabilization. The research provides theoretical basis for the LOS stabilization control to isolate the LOS from the disturbance and vibration of carrier.


Author(s):  
Oleg Nesterenko ◽  
Lev Ryzhkov ◽  
Vladyslav Osokin

The article considers the development of a mathematical model of the stabilization and rotation system in the modes of stabilization, targeting, auto-tracking of the target and electrical arrest. The output signals shall be signals proportional to the components of the angular velocities of the line of sight, the angles of pitch and dash of deviation around the axes of the gyrosystem and the angles of inconsistency of the line of sight relative to the optical axis of the homing head. The system of cardan suspension of the stabilization and rotation system is considered, where the actuators are located on the axes of rotation of the outer and inner frames of the cardan suspension. The homing head is mounted on the inner frame. The inner frame is a gyrostabilized platform. Depending on the mode of operation of the stabilization and rotation system: in the stabilization mode, the coordinate system that is stabilized is assumed to be stationary in inertial space; in the auto-tracking mode of the target, the coordinate system that is stabilized by Oxyz is returned according to the change of direction to the target; in the mode of electrical locking, the axes of the coordinate system which is stabilized by Oxyz coincide with the axes of Oxoyozo connected to the body of the main product. To obtain differential equations, the projections of the total vector of the kinetic moment of the inner and outer frames on the axis of the outer frame are taken and written according to the theorem on the change of the kinetic moment of the considered system relative to the axes of suspensions. The total moments of external forces applied to the outer and inner frames around their axes of rotation, which have the following components: moments of actuators, moments of viscous and dry friction, imbalance and other unaccounted for factors around the axes of the outer and inner frames . The moments of the forces of viscous and dry friction are presented in the classical form, taking into account the signs when changing the direction of movement. The mass of the inner frame with all devices mounted on it, and the mass of the entire movable system (outer and inner frames), as well as the radius vector characterizing the displacement of the center of mass, give a static imbalance of the movable system relative to the suspension axis of the i-th frame are components imbalance. The scientific novelty of the work is to obtain a mathematical model for a particular product, as well as the practical feasibility of their application. The result is a differential equation that fully describes this system of stabilization and rotation, takes into account the parameters of actuators, turbulent moments, as well as random effects and can be used depending on the tasks.


2019 ◽  
Vol 1203 ◽  
pp. 012043
Author(s):  
T M Ledeneva ◽  
N A Kaplieva ◽  
M A Sergienko ◽  
E E Chupandina

Sign in / Sign up

Export Citation Format

Share Document